OCRRouter

Hunyuan OCR vs Florence-2

Pick Hunyuan OCR for photos, scene text, image translation, low-resource scripts and structured output such as Markdown, HTML, LaTeX or JSON, if you are outside the EU, UK and South Korea. Pick Florence-2 for small, MIT-licensed OCR of English scene text and short labels with line boxes, especially when the same model must also do captioning or detection. Avoid Florence-2 for full pages, CJK text and handwriting.

Hunyuan OCRtencent/hunyuan-ocrFlorence-2microsoft/florence-2
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed1.5 s / page0.8 s / page
Best forChinese documents and photosLightweight OCR with boxes
InputsPDF, imagesimages
Languages100+ languagesEnglish
Max pages per request500500
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose Hunyuan OCR if

  • You need structured output: Markdown, HTML, LaTeX, JSON, plain text or bounding boxes.
  • You work with Chinese or other non-Latin text, low-resource scripts or ancient scripts, or need image translation.
  • You want one ~1B model for parsing, text spotting, extraction and translation, with images up to 4K and a 128K context window in v1.5.

Choose Florence-2 if

  • You need a permissive MIT licence with no regional exclusions or user-count limits.
  • You want the smallest footprint: 0.23B base or 0.77B large, run through Transformers.
  • You need line-level quadrilateral boxes for scene text and short labels, or the same model must also caption, detect and ground objects.

Key differences

Hunyuan OCRFlorence-2
LicenceTencent Hunyuan Community License. Excludes the EU, UK and South Korea. Separate licence needed above 100M monthly active users.MIT
Model size~1B parameters0.23B (base), 0.77B (large)
How you run itSelf-hosted via vLLM, Transformers or llama.cpp. CUDA 13 recommended for the unified vLLM environment. llama.cpp GGUF path for CPU, consumer GPU or laptop.Self-hosted via Transformers
Output formatsMarkdown, HTML, LaTeX, JSON, plain text, bounding boxesPlain text and bounding boxes. No Markdown, tables or LaTeX.
ScopeDocument parsing, text spotting, information extraction and image translation in one modelOCR and OCR with regions, plus captioning, detection and grounding
Chinese and CJK textNot publishedChinese output mostly wrong. The vocabulary lacks CJK characters.
Known failureParseBench-2 overall is 67.11. Transformers and vLLM outputs differed in accuracy in the archived 1.0 note.Spelling errors and missing spaces on cursive handwriting and French text in a Hugging Face blog test.

Sources

What each one is

Hunyuan OCR

Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.

Hunyuan OCR details

Florence-2

Small Microsoft vision model (0.23B and 0.77B) with OCR and OCR-with-regions tasks that return text with boxes.

Florence-2 details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 10 files at onceNo file?

Use one, fall back to the other

{"model": "tencent/hunyuan-ocr","fallbacks": ["microsoft/florence-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Hunyuan OCR alternativesFlorence-2 alternativesBest OCR models in 2026